Quantum Machine Learning- Prospects and Challenges
Offered By: Simons Institute via YouTube
Course Description
Overview
Explore the potential and limitations of quantum machine learning in this 39-minute lecture by Iordanis Kerenidis from CNRS and QC Ware. Delve into the reasons for optimism and caution in the field, and examine various classification techniques including distance-based methods, quantum neural networks, and training classical neural networks. Investigate dimensionality reduction in both classical and quantum contexts, and learn about the challenges of loading data for quantum machine learning and extracting classical information from quantum states. Gain insights into the benchmarking process for quantum machine learning algorithms and understand the current state of this emerging field.
Syllabus
Intro
Reasons for optimist keep working on it
Reasons for caution keep working on it
Classification: Distance-based
Classification: Quantum Neural Networks
Classification: Training classical Neural Networks
Classification: Dimensionality Reduction
Classification: Quantum Dimensionality Reduction
Loading data for Quantum Machine Learning
Getting classical information from quantum states
Benchmarking QML
Taught by
Simons Institute
Related Courses
Big Data Analytics in HealthcareGeorgia Institute of Technology via Udacity Introduction to Recommender Systems
University of Minnesota via Coursera Поиск структуры в данных
Moscow Institute of Physics and Technology via Coursera Materials Data Sciences and Informatics
Georgia Institute of Technology via Coursera Matrix Factorization and Advanced Techniques
University of Minnesota via Coursera